检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,976 篇 会议
38 篇 期刊文献
7 册 图书

馆藏范围

3,021 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,758 篇 工学
- 1,406 篇 计算机科学与技术...
- 684 篇 软件工程
- 490 篇 电气工程
- 397 篇 信息与通信工程
- 203 篇 控制科学与工程
- 130 篇 生物工程
- 77 篇 电子科学与技术（可...
- 65 篇 生物医学工程（可授...
- 58 篇 机械工程
- 54 篇 仪器科学与技术
- 48 篇 光学工程
- 33 篇 网络空间安全
- 30 篇 动力工程及工程热...
- 23 篇 安全科学与工程
- 22 篇 材料科学与工程（可...
- 22 篇 化学工程与技术
- 20 篇 测绘科学与技术
- 19 篇 石油与天然气工程
515 篇 理学
- 224 篇 物理学
- 189 篇 数学
- 143 篇 生物学
- 58 篇 统计学（可授理学、...
- 40 篇 系统科学
- 27 篇 化学
202 篇 管理学
- 134 篇 管理科学与工程(可...
- 81 篇 图书情报与档案管...
- 31 篇 工商管理
135 篇 医学
- 112 篇 临床医学
- 38 篇 基础医学(可授医学...
37 篇 法学
- 20 篇 社会学
18 篇 文学
14 篇 农学
10 篇 教育学
9 篇 经济学
2 篇 军事学

主题

591 篇 neural networks
180 篇 training
169 篇 artificial neura...
168 篇 deep learning
142 篇 computational mo...
129 篇 feature extracti...
123 篇 convolutional ne...
115 篇 neural network
88 篇 machine learning
87 篇 neurons
86 篇 parallel process...
79 篇 deep neural netw...
75 篇 computer archite...
74 篇 distributed comp...
73 篇 accuracy
65 篇 signal processin...
62 篇 distributed proc...
61 篇 data models
60 篇 recurrent neural...
51 篇 convolutional ne...

机构

11 篇 institute of inf...
9 篇 school of cyber ...
8 篇 univ chinese aca...
8 篇 natl univ def te...
7 篇 college of compu...
7 篇 carnegie mellon ...
7 篇 department of co...
7 篇 national laborat...
7 篇 beijing universi...
7 篇 natl univ def te...
6 篇 shanghai jiao to...
6 篇 the islamic univ...
5 篇 science and tech...
5 篇 ibm tj watson re...
5 篇 school of inform...
5 篇 king saud univer...
5 篇 shandong normal ...
5 篇 kaust thuwal
5 篇 university of ch...
5 篇 natl univ def te...

作者

8 篇 li dongsheng
8 篇 dou yong
8 篇 jie liu
6 篇 richtarik peter
6 篇 ribeiro alejandr...
6 篇 liu jie
6 篇 niu xin
6 篇 yong dou
6 篇 shulian yang
6 篇 zhang wei
5 篇 ryabinin max
5 篇 segarra santiago
5 篇 lai zhiquan
5 篇 ding bo
5 篇 qiao peng
5 篇 xu jiren
5 篇 kokkinos yiannis
5 篇 peng yuxing
5 篇 wang huaimin
5 篇 li aiping

语言

2,814 篇 英文
199 篇 其他
11 篇 中文
2 篇 土耳其文

检索条件"任意字段=Conference on Neural Network and Distributed Processing"

共 3021 条记录，以下是1221-1230 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

distributed Scheduling Using Graph neural networks

Distributed Scheduling Using Graph Neural Networks

引用

IEEE International conference on Acoustics, Speech and Signal processing

作者： Zhongyuan Zhao Gunjan Verma Chirag Rao Ananthram Swami Santiago Segarra Rice University USA US Army’s CCDC Army Research Laboratory USA

A fundamental problem in the design of wireless networks is to efficiently schedule transmission in a distributed manner. The main challenge stems from the fact that optimal link scheduling involves solving a maximum weighted independent set (MWIS) problem, which is NP-hard. For practical link scheduling schemes, distributed greedy approaches are commonly used to approximate the solution of the MWIS problem. However, these greedy schemes mostly ignore important topological information of the wireless networks. To overcome this limitation, we propose a distributed MWIS solver based on graph convolutional networks (GCNs). In a nutshell, a trainable GCN module learns topology-aware node embeddings that are combined with the network weights before calling a greedy solver. In small- to middle-sized wireless networks with tens of links, even a shallow GCN-based MWIS scheduler can leverage the topological information of the graph to reduce in half the suboptimality gap of the distributed greedy solver with good generalizability across graphs and minimal increase in complexity.

关键词： Schedules Convolution Wireless networks conferences Graph neural networks Acoustics Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Benchmarking neural network architectures for acoustic sensor networks 13

Benchmarking neural network architectures for acoustic senso...

引用

13th ITG conference on Speech Communication

作者： Ebbers, Janek Heitkaemper, Jens Schmalenstroeer, Joerg Haeb-Umbach, Reinhold Department for Communication Engineering Paderborn University Germany

ISBN: (纸本)9783800747672

Due to their distributed nature wireless acoustic sensor networks offer great potential for improved signal acquisition, processing and classification for applications such as monitoring and surveillance, home automation, or hands-free telecommunication. To reduce the communication demand with a central server and to raise the privacy level it is desirable to perform processing at node level. The limited processing and memory capabilities on a sensor node, however, stand in contrast to the compute and memory intensive deep learning algorithms used in modern speech and audio processing. In this work, we perform benchmarking of commonly used convolutional and recurrent neural network architectures on a Raspberry Pi based acoustic sensor node. We show that it is possible to run medium-sized neural network topologies used for speech enhancement and speech recognition in real time. For acoustic event recognition, where predictions in a lower temporal resolution are sufficient, it is even possible to run current state-of-the-art deep convolutional models with a real-time-factor of 0.11. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

An Efficient ADMM-aided Deep Learning-based Signal Detector for Uplink Massive MIMO

An Efficient ADMM-aided Deep Learning-based Signal Detector ...

引用

IEEE International conference on Communications (IEEE ICC) / Workshop on NOMA for 5G and Beyond

作者： Huang, Hongji Cioffi, John M. Hashemi, Seyyed Ali MIT Dept Elect Engn Cambridge MA 02139 USA Stanford Univ Dept Elect Engn Stanford CA 94305 USA

ISBN: (纸本)9781728174402

This paper provides an efficient Alternating Direction Method of Multipliers (ADMM)-aided deep neural network (DNN) framework for signal detection based on uplink Massive Multiple Input Multiple Output (Massive MIMO) systems. Since ADMM is a good candidate for distributed computing and solving complicated problems, it is integrated into a DNN to enhance the DNN's learning performance. Not only can the developed DNN emulate the ADMM operations with fast speed and good performance, but also it fully exploits the characteristics of the samples for signal detection. Specifically, the DNN comprises two parts: the data-processing module is adopted for making the samples sparse and the iteration-mapping module reconstructs transmit signals with the aid of the ADMM. Then, a learning policy is proposed, which is composed of an offline learning method and a lifelong learning-based online method. Simulation results show that the proposed scheme is capable of reducing signal-detection error compared with previous work. Also, it is corroborated that the proposed scheme requires relatively low computational complexity.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Algorithm for Multi-Fame Image Super-Resolution under Applicative Noise Based on a Convolutional neural network 2

An Algorithm for Multi-Fame Image Super-Resolution under App...

引用

2nd International conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2020

作者： Savvin, Sergey Sirota, Alexander Voronezh State University Faculty of Computer Sciences Voronezh Russia

ISBN: (纸本)9781728188409

The paper considers the problem of multi-frame super-resolution under applicative noise which generates distributed regions of outlying observations (damaged regions) in initial low resolution images. It analyses the existing solutions to the problem based on using recurrent algorithms of optimal filtering of a sequence of low resolution images. The paper also considers the existing super-resolution algorithms based on convolutional neural networks and deep learning models. A new approach and a corresponding image processing scheme is suggested for multi-frame image super-resolution under applicative noise based on using a convolutional neural network. The paper presents the results of the experiment conducted in order to compare the considered approaches to multi-frame image super-resolution by means of a sequence of low resolution frames under applicative noise. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

End-to-End Performance Optimization for Training Streaming Convolutional neural networks using Billion-Pixel Whole-Slide Images

End-to-End Performance Optimization for Training Streaming C...

引用

IEEE International conference on Big Data

作者： Liang-Wei Tao An-Fong Hwu Yu-Jen Huang Chi-Chung Chen Chao-Yuan Yeh Shih-Hao Hung National Taiwan University Taipei Taiwan aetherAI Co. Ltd Taipei Taiwan

ISBN: (纸本)9781665445993

The combination of digital pathology and artificial intelligence attracts more and more attention. In order to take into account the global and detailed textural information, recent works proposed to use whole-slide images (WSI) with more than 10 million pixels to train artificial neural networks in pursuit of a high-precision model. However, such an approach faces new technical challenges. When researchers conduct neural network training on a graphics processing unit (GPU), the extremely high spatial resolution of WSI and the large amount of intermediate data generated during the training process exceed the memory capacity of the GPU. Therefore, streaming convolutional neural network (SCNN) was proposed to disassemble a large image into multiple smaller patches that can be forward and backward propagated under the limitation of GPU memory during the training process. However, in a multi-GPU high-performance computing (HPC) system, when the central processing unit (CPU) performs data preprocessing for the distributed training of multiple GPUs, decoding large images and data augmentation consume a lot of memory and CPU time, resulting in a performance *** paper first presents a multithreaded image decoder optimized for multi-core CPUs to speedup WSI loading. We also propose a patch-level data augmentation algorithm and implement it on a dedicated GPU to distribute the augmented data to other GPUs for training the SCNN. We use the above method to train the ResNet-50 SCNN model by learning from the TCGA-LUAD and TCGA-LUSC datasets published by The Cancer Genome Atlas. In comparison to training the SCNN on multiple GPUs using the regular distributed data parallelism, our method can save up to 92.8% of memory and increase the training speed by up to 242.5% when training with 8 A100 GPUs on the NVIDIA DGX-A100 system.

关键词： Training Pathology Graphics processing units distributed databases Streaming media Big Data Central processing Unit

来源：评论

学校读者我要写书评

暂无评论

A Normal Approach of Online Signature Using Stroke Point Warping - A Survey 3rd

A Normal Approach of Online Signature Using Stroke Point War...

引用

International conference on Computational Vision and Bio-Inspired Computing (ICCVBIC)

作者： Shyry, S. Prayla Srivanth, P. Thomson, Derrick Sathyabama Inst Sci & Technol Dept Comp Sci Engn Chennai Tamil Nadu India

ISBN: (纸本)9783030372187;9783030372170

In today's world, the method to identify the online verification technique is appeared with the help of the signature device. Some common human biometrics include iris recognition, retinal scanner, voice detection, fingerprint detector, and thumbprint detection. Fingerprint detector is used in the mobile devices. Traditionally, due to the in-built inconsistency of the collected signature, a normal procedure known as Stroke Point Warping (SPW) was recommended. In the proposed system, a normal methodology called DSUM (distributed Data Split up Model) for signature verification is used to improve the accuracy level of the extracted features. In this DSUM model, the signature area is being extracted and splitted into N number of blocks. For studying the features accurately each N blocks are being fetched up for multi modal feature extraction. The neural network (decision making) is being done by using the multiple scores and featured vectors. Nowadays, neural networks and deep learning gives good solution for problems in image identification, voice detection and natural language processing.

关键词： Biometrics distributed Data Split Up Model (DSUM) Inherent variability neural network Stroke Point Warping (SPW)

来源：评论

学校读者我要写书评

暂无评论

Unwrapping SAR interferograms with localized subsidence signal using deep neural network

Unwrapping SAR interferograms with localized subsidence sign...

引用

EUSAR 2021;13th European conference on Synthetic Aperture Radar

作者： Zhipeng Wu Teng Wang Robert Wang

Phase unwrapping is an indispensable processing step of InSAR. However, conventional methods often underestimate the deformation due to severe noise and/or dense fringes. Here, we develop a new deep neural network to unwrap interferograms with localized subsidence signal. We train the network using synthetic interferograms with two-dimensional Gaussian shape subsidence and complex Gaussian noises, and apply the network to real interferograms with localized mining subsidence. The proposed method outperforms the standard methods by 76.3% on synthetic interferograms and ~50-times faster on real interferograms. The promising result shows the potential for rapid monitoring and quantification local deformation distributed in large area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quantized neural Scene Representations

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quan...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Prabhudesai, Mihir Lal, Shamit Tung, Hsiao-Yu Fish Harley, Adam W. Potdar, Shubhankar Fragkiadaki, Katerina Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781728193601

Concept learning lies at the very heart of intelligence, providing organizing principles with which to comprehend the world (6). Most computer vision models learn concept classifiers or detectors using labelled examples of object boxes, poses and categories. Self-supervised or unsupervised approaches mostly focus on (pre)training CNNs on auxiliary pretext tasks to lessen the need for human labels for a downstream recognition task. The visual "concepts" learnt from pretext tasks are implicit and represented as distributed neural CNN activations (7). We see the following limitations with representing concepts (solely) as neural activations across multiple layers of a deep network: i) visual memory and computation are not separated (3), which means that computation increases exponentially with the number of visual concepts learnt, ii) concepts are not stored somewhere and cannot be referred to or retrieved on demand, iii) the number of concepts cannot increase automatically based on new visual experiences, rather it is determined by the processing architecture;this misaligns with the idea that animals are capable of spontaneous concept instantiation in novel scenes (2), iv) concepts cannot be mentally manipulated by imagining variations, transformations or mental simulations (8), v) concepts do not have any spatial dimension and are hard to use for spatial reasoning. © 2020 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

AccDP: Accelerated Data-Parallel distributed DNN Training for Modern GPU-Based HPC Clusters

AccDP: Accelerated Data-Parallel Distributed DNN Training fo...

引用

International conference on High Performance Computing

作者： Nawras Alnaasan Arpan Jain Aamir Shafi Hari Subramoni Dhabaleswar K Panda Department of Computer Science and Engineering The Ohio State University Columbus Ohio USA

Deep Learning (DL) has become a prominent machine learning technique due to the availability of efficient computational resources in the form of Graphics processing Units (GPUs), large-scale datasets and a variety of models. The newer generation of GPUs are being designed with special emphasis on optimizing performance for DL applications. Also, the availability of easy-to-use DL frameworks—like PyTorch and TensorFlow— has enhanced productivity of domain experts to work on their custom DL applications from diverse domains. However, existing Deep neural network (DNN) training approaches may not fully utilize the newly emerging powerful GPUs like the NVIDIA A100—this is the primary issue that we address in this paper. Our motivating analyses show that the GPU utilization on NVIDIA A100 can be as low as 43% using traditional DNN training approaches for small-to-medium DL models and input data size. This paper proposes AccDP—a data-parallel distributed DNN training approach—to accelerate GPU-based DL applications. AccDP exploits the Message Passing Interface (MPI) communication library coupled with the NVIDIA’s Multi-Process Service (MPS) to increase the amount of work assigned to parallel GPUs resulting in higher utilization of compute resources. We evaluate our proposed design on different small-to-medium DL models and input sizes on the state-of-the-art HPC clusters. By injecting more parallelism into DNN training using our approach, the evaluation shows up to 58% improvement in training performance on a single GPU and up to 62% on 16 GPUs compared to regular DNN training. Furthermore, we conduct an in-depth characterization to determine the impact of several DNN training factors and best practices—including the batch size and the number of data loading workers— to optimally utilize GPU devices. To the best of our knowledge, this is the first work that explores the use of MPS and MPI to maximize the utilization of GPUs in distributed DNN training.

关键词： Training Deep learning Productivity Performance evaluation Computational modeling Message passing neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Parametric Versus Non-Parametric Text Classification Algorithms 15

A Comparative Study of Parametric Versus Non-Parametric Text...

引用

15th International conference on Development and Application Systems (DAS)

作者： Chistol, Mihaela Stefan Cel Mare Univ Suceava Suceava Romania

ISBN: (纸本)9781728168708

Evolution of modern technologies allowed to store the text in various digital formats such as e-mails, e-documents, libraries, etc. The amount of text data that is produced daily is increasing dramatically. Discovering useful patterns in text that can be represented in unstructured, semi-structured or structured format is a difficult task that requires a good understanding of machine learning algorithms. Finding a suitable algorithm for text mining tasks such as classification, clustering or natural language processing is a demanding situation that tests researchers' abilities. This paper provides an overview of the text mining process also, presents a comparison of the performance and limitations of two predictive models generated using the parametric Naive Bayes algorithm and non-parametric Deep Learning neural network. RapidMiner data science software platform has been used for models' implementations and e-mail classification.

关键词： text classification text mining machine learning Naive Bayes neural network performance evaluation

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共303页 << < 119 120 121 122 123 124 125 126 127 128 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：